Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5265 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0601. Min Act: -0.0002

Data Index: 402258 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0629. Min Act: -0.0002

Data Index: 701726 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1129148 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0655. Min Act: -0.0002

Data Index: 678514 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0597. Min Act: -0.0002

Data Index: 33168 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0599. Min Act: -0.0002

Data Index: 324122 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1106250 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0529. Min Act: -0.0002

Data Index: 413396 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0567. Min Act: -0.0002

Data Index: 725099 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0538. Min Act: -0.0002

Data Index: 558419 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1102265 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1080385 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0528. Min Act: -0.0002

Data Index: 713269 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0502. Min Act: -0.0002

Data Index: 611781 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1329929 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1027484 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0498. Min Act: -0.0002

Data Index: 691478 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1190996 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0492. Min Act: -0.0002

Data Index: 450185 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1113861 (C4 (Web Text))

Max Activating Token Index: 594